I know that reinforcement learning has been used to solve the inverted pendulum problem.

Can supervised learning be used to solve the inverted pendulum problem?

For example, there could be an interface (e.g. a joystick) with the cart-pole system, which the human can use to balance the pole and, at the same time, collect a dataset for supervised learning. Has this been done before?

  • 1
    $\begingroup$ Yes, you can do it, for example this paper uses YouTube videos to learn how to play difficult game Montezuma's Revenge $\endgroup$ – Brale Nov 29 '19 at 8:45

Of course you can, and yes this has been researched and done before. By using supervised learning, you give the machine some data, and it will try to figure the best way to analyze and predict the next movement in case of an inverted pendulum problem. I found a complete paper for this problem. Here is the BibTex:

author = {Mladenov, Valeri and Tsenov, Georgi and Ekonomou, Lambros and Harkiolakis, Nicholas and Karampelas, Panagiotis},
year = {2009},
month = {01},
pages = {},
title = {Neural network control of an inverted pendulum on a cart},
volume = {8}

This is for the link:


| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.